RubyGems - openai - Versions diffs - 0.92.0 → 0.94.0 - Mend

openai 0.92.0 → 0.94.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (1311) hide show

data/sig/openai/models/audio/transcription_create_params.rbs CHANGED Viewed

@@ -23,58 +23,236 @@ module OpenAI
         extend OpenAI::Internal::Type::RequestParameters::Converter
         include OpenAI::Internal::Type::RequestParameters
+        # The audio file object (not file name) to transcribe, in one of these formats:
+        # flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm. The request must include
+        # enough format metadata for the file to be identified. We recommend an
+        # extension-bearing filename and an appropriate content type.
+        #
+        # `String`, `StringIO`, and pathless `IO` inputs are sent with generic upload
+        # metadata. Use `OpenAI::FilePart` when you need to override the filename or
+        # content type.
         attr_accessor file: OpenAI::Internal::file_input
+        # ID of the model to use. The options are `gpt-transcribe`, `gpt-4o-transcribe`,
+        # `gpt-4o-mini-transcribe`, `gpt-4o-mini-transcribe-2025-12-15`, `whisper-1`
+        # (which is powered by our open source Whisper V2 model), and
+        # `gpt-4o-transcribe-diarize`.
         attr_accessor model: OpenAI::Models::Audio::TranscriptionCreateParams::model
+        # Controls how the audio is cut into chunks. When set to `"auto"`, the server
+        # first normalizes loudness and then uses voice activity detection (VAD) to choose
+        # boundaries. `server_vad` object can be provided to tweak VAD detection
+        # parameters manually. If unset, the audio is transcribed as a single block.
+        # Required when using `gpt-4o-transcribe-diarize` for inputs longer than 30
+        # seconds.
         attr_accessor chunking_strategy: OpenAI::Models::Audio::TranscriptionCreateParams::chunking_strategy?
+        # Additional information to include in the transcription response. `logprobs` will
+        # return the log probabilities of the tokens in the response to understand the
+        # model's confidence in the transcription. `logprobs` only works with
+        # response_format set to `json` and only with the models `gpt-4o-transcribe`,
+        # `gpt-4o-mini-transcribe`, and `gpt-4o-mini-transcribe-2025-12-15`. This field is
+        # not supported when using `gpt-4o-transcribe-diarize`.
         attr_reader include: ::Array[OpenAI::Models::Audio::transcription_include]?
+        # Additional information to include in the transcription response. `logprobs` will
+        # return the log probabilities of the tokens in the response to understand the
+        # model's confidence in the transcription. `logprobs` only works with
+        # response_format set to `json` and only with the models `gpt-4o-transcribe`,
+        # `gpt-4o-mini-transcribe`, and `gpt-4o-mini-transcribe-2025-12-15`. This field is
+        # not supported when using `gpt-4o-transcribe-diarize`.
         def include=: (
           ::Array[OpenAI::Models::Audio::transcription_include]
         ) -> ::Array[OpenAI::Models::Audio::transcription_include]
+        # Words or phrases to guide transcription of the input audio. Supported by
+        # `gpt-transcribe`.
         attr_reader keywords: ::Array[String]?
+        # Words or phrases to guide transcription of the input audio. Supported by
+        # `gpt-transcribe`.
         def keywords=: (::Array[String]) -> ::Array[String]
+        # Optional list of speaker names that correspond to the audio samples provided in
+        # `known_speaker_references[]`. Each entry should be a short identifier (for
+        # example `customer` or `agent`). Up to 4 speakers are supported.
         attr_reader known_speaker_names: ::Array[String]?
+        # Optional list of speaker names that correspond to the audio samples provided in
+        # `known_speaker_references[]`. Each entry should be a short identifier (for
+        # example `customer` or `agent`). Up to 4 speakers are supported.
         def known_speaker_names=: (::Array[String]) -> ::Array[String]
+        # Optional list of audio samples (as
+        # [data URLs](https://developer.mozilla.org/en-US/docs/Web/HTTP/Basics_of_HTTP/Data_URLs))
+        # that contain known speaker references matching `known_speaker_names[]`. Each
+        # sample must be between 2 and 10 seconds, and can use any of the same input audio
+        # formats supported by `file`.
         attr_reader known_speaker_references: ::Array[String]?
+        # Optional list of audio samples (as
+        # [data URLs](https://developer.mozilla.org/en-US/docs/Web/HTTP/Basics_of_HTTP/Data_URLs))
+        # that contain known speaker references matching `known_speaker_names[]`. Each
+        # sample must be between 2 and 10 seconds, and can use any of the same input audio
+        # formats supported by `file`.
         def known_speaker_references=: (::Array[String]) -> ::Array[String]
+        # The language of the input audio. Supplying the input language in
+        # [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) (e.g. `en`)
+        # format will improve accuracy and latency.
         attr_reader language: String?
+        # The language of the input audio. Supplying the input language in
+        # [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) (e.g. `en`)
+        # format will improve accuracy and latency.
         def language=: (String) -> String
+        # Possible languages of the input audio, in
+        # [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) format.
+        # Supported by `gpt-transcribe`.
         attr_reader languages: ::Array[String]?
+        # Possible languages of the input audio, in
+        # [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) format.
+        # Supported by `gpt-transcribe`.
         def languages=: (::Array[String]) -> ::Array[String]
+        # An optional text to guide the model's style or continue a previous audio
+        # segment. The
+        # [prompt](https://developers.openai.com/api/docs/guides/speech-to-text#prompting)
+        # should match the audio language. This field is not supported when using
+        # `gpt-4o-transcribe-diarize`.
         attr_reader prompt: String?
+        # An optional text to guide the model's style or continue a previous audio
+        # segment. The
+        # [prompt](https://developers.openai.com/api/docs/guides/speech-to-text#prompting)
+        # should match the audio language. This field is not supported when using
+        # `gpt-4o-transcribe-diarize`.
         def prompt=: (String) -> String
+        # The format of the output, in one of these options: `json`, `text`, `srt`,
+        # `verbose_json`, `vtt`, or `diarized_json`. For `gpt-4o-transcribe` and
+        # `gpt-4o-mini-transcribe`, the only supported format is `json`. For
+        # `gpt-4o-transcribe-diarize`, the supported formats are `json`, `text`, and
+        # `diarized_json`, with `diarized_json` required to receive speaker annotations.
         attr_reader response_format: OpenAI::Models::audio_response_format?
+        # The format of the output, in one of these options: `json`, `text`, `srt`,
+        # `verbose_json`, `vtt`, or `diarized_json`. For `gpt-4o-transcribe` and
+        # `gpt-4o-mini-transcribe`, the only supported format is `json`. For
+        # `gpt-4o-transcribe-diarize`, the supported formats are `json`, `text`, and
+        # `diarized_json`, with `diarized_json` required to receive speaker annotations.
         def response_format=: (
           OpenAI::Models::audio_response_format
         ) -> OpenAI::Models::audio_response_format
+        # The sampling temperature, between 0 and 1. Higher values like 0.8 will make the
+        # output more random, while lower values like 0.2 will make it more focused and
+        # deterministic. If set to 0, the model will use
+        # [log probability](https://en.wikipedia.org/wiki/Log_probability) to
+        # automatically increase the temperature until certain thresholds are hit.
         attr_reader temperature: Float?
+        # The sampling temperature, between 0 and 1. Higher values like 0.8 will make the
+        # output more random, while lower values like 0.2 will make it more focused and
+        # deterministic. If set to 0, the model will use
+        # [log probability](https://en.wikipedia.org/wiki/Log_probability) to
+        # automatically increase the temperature until certain thresholds are hit.
         def temperature=: (Float) -> Float
+        # The timestamp granularities to populate for this transcription.
+        # `response_format` must be set `verbose_json` to use timestamp granularities.
+        # Either or both of these options are supported: `word`, or `segment`. Note: There
+        # is no additional latency for segment timestamps, but generating word timestamps
+        # incurs additional latency. This option is not available for
+        # `gpt-4o-transcribe-diarize`.
         attr_reader timestamp_granularities: ::Array[OpenAI::Models::Audio::TranscriptionCreateParams::timestamp_granularity]?
+        # The timestamp granularities to populate for this transcription.
+        # `response_format` must be set `verbose_json` to use timestamp granularities.
+        # Either or both of these options are supported: `word`, or `segment`. Note: There
+        # is no additional latency for segment timestamps, but generating word timestamps
+        # incurs additional latency. This option is not available for
+        # `gpt-4o-transcribe-diarize`.
         def timestamp_granularities=: (
           ::Array[OpenAI::Models::Audio::TranscriptionCreateParams::timestamp_granularity]
         ) -> ::Array[OpenAI::Models::Audio::TranscriptionCreateParams::timestamp_granularity]
+        # @param file
+        #   The audio file object (not file name) to transcribe, in one of these formats:
+        #   flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm. The request must include
+        #   enough format metadata for the file to be identified. We recommend an
+        #   extension-bearing filename and an appropriate content type.
+        #
+        #   `String`, `StringIO`, and pathless `IO` inputs are sent with generic upload
+        #   metadata. Use `OpenAI::FilePart` when you need to override the filename or
+        #   content type.
+        # @param model
+        #   ID of the model to use. The options are `gpt-transcribe`, `gpt-4o-transcribe`,
+        #   `gpt-4o-mini-transcribe`, `gpt-4o-mini-transcribe-2025-12-15`, `whisper-1`
+        #   (which is powered by our open source Whisper V2 model), and
+        #   `gpt-4o-transcribe-diarize`.
+        # @param chunking_strategy
+        #   Controls how the audio is cut into chunks. When set to `"auto"`, the server
+        #   first normalizes loudness and then uses voice activity detection (VAD) to choose
+        #   boundaries. `server_vad` object can be provided to tweak VAD detection
+        #   parameters manually. If unset, the audio is transcribed as a single block.
+        #   Required when using `gpt-4o-transcribe-diarize` for inputs longer than 30
+        #   seconds.
+        # @param include
+        #   Additional information to include in the transcription response. `logprobs` will
+        #   return the log probabilities of the tokens in the response to understand the
+        #   model's confidence in the transcription. `logprobs` only works with
+        #   response_format set to `json` and only with the models `gpt-4o-transcribe`,
+        #   `gpt-4o-mini-transcribe`, and `gpt-4o-mini-transcribe-2025-12-15`. This field is
+        #   not supported when using `gpt-4o-transcribe-diarize`.
+        # @param keywords
+        #   Words or phrases to guide transcription of the input audio. Supported by
+        #   `gpt-transcribe`.
+        # @param known_speaker_names
+        #   Optional list of speaker names that correspond to the audio samples provided in
+        #   `known_speaker_references[]`. Each entry should be a short identifier (for
+        #   example `customer` or `agent`). Up to 4 speakers are supported.
+        # @param known_speaker_references
+        #   Optional list of audio samples (as
+        #   [data URLs](https://developer.mozilla.org/en-US/docs/Web/HTTP/Basics_of_HTTP/Data_URLs))
+        #   that contain known speaker references matching `known_speaker_names[]`. Each
+        #   sample must be between 2 and 10 seconds, and can use any of the same input audio
+        #   formats supported by `file`.
+        # @param language
+        #   The language of the input audio. Supplying the input language in
+        #   [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) (e.g. `en`)
+        #   format will improve accuracy and latency.
+        # @param languages
+        #   Possible languages of the input audio, in
+        #   [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) format.
+        #   Supported by `gpt-transcribe`.
+        # @param prompt
+        #   An optional text to guide the model's style or continue a previous audio
+        #   segment. The
+        #   [prompt](https://developers.openai.com/api/docs/guides/speech-to-text#prompting)
+        #   should match the audio language. This field is not supported when using
+        #   `gpt-4o-transcribe-diarize`.
+        # @param response_format
+        #   The format of the output, in one of these options: `json`, `text`, `srt`,
+        #   `verbose_json`, `vtt`, or `diarized_json`. For `gpt-4o-transcribe` and
+        #   `gpt-4o-mini-transcribe`, the only supported format is `json`. For
+        #   `gpt-4o-transcribe-diarize`, the supported formats are `json`, `text`, and
+        #   `diarized_json`, with `diarized_json` required to receive speaker annotations.
+        # @param temperature
+        #   The sampling temperature, between 0 and 1. Higher values like 0.8 will make the
+        #   output more random, while lower values like 0.2 will make it more focused and
+        #   deterministic. If set to 0, the model will use
+        #   [log probability](https://en.wikipedia.org/wiki/Log_probability) to
+        #   automatically increase the temperature until certain thresholds are hit.
+        # @param timestamp_granularities
+        #   The timestamp granularities to populate for this transcription.
+        #   `response_format` must be set `verbose_json` to use timestamp granularities.
+        #   Either or both of these options are supported: `word`, or `segment`. Note: There
+        #   is no additional latency for segment timestamps, but generating word timestamps
+        #   incurs additional latency. This option is not available for
+        #   `gpt-4o-transcribe-diarize`.
         def initialize: (
           file: OpenAI::Internal::file_input,
           model: OpenAI::Models::Audio::TranscriptionCreateParams::model,
@@ -133,20 +311,47 @@ module OpenAI
             }
           class VadConfig < OpenAI::Internal::Type::BaseModel
+            # Must be set to `server_vad` to enable manual chunking using server side VAD.
             attr_accessor type: OpenAI::Models::Audio::TranscriptionCreateParams::ChunkingStrategy::VadConfig::type_
+            # Amount of audio to include before the VAD detected speech (in milliseconds).
             attr_reader prefix_padding_ms: Integer?
+            # Amount of audio to include before the VAD detected speech (in milliseconds).
             def prefix_padding_ms=: (Integer) -> Integer
+            # Duration of silence to detect speech stop (in milliseconds). With shorter values
+            # the model will respond more quickly, but may jump in on short pauses from the
+            # user.
             attr_reader silence_duration_ms: Integer?
+            # Duration of silence to detect speech stop (in milliseconds). With shorter values
+            # the model will respond more quickly, but may jump in on short pauses from the
+            # user.
             def silence_duration_ms=: (Integer) -> Integer
+            # Sensitivity threshold (0.0 to 1.0) for voice activity detection. A higher
+            # threshold will require louder audio to activate the model, and thus might
+            # perform better in noisy environments.
             attr_reader threshold: Float?
+            # Sensitivity threshold (0.0 to 1.0) for voice activity detection. A higher
+            # threshold will require louder audio to activate the model, and thus might
+            # perform better in noisy environments.
             def threshold=: (Float) -> Float
+            # @param type
+            #   Must be set to `server_vad` to enable manual chunking using server side VAD.
+            # @param prefix_padding_ms
+            #   Amount of audio to include before the VAD detected speech (in milliseconds).
+            # @param silence_duration_ms
+            #   Duration of silence to detect speech stop (in milliseconds). With shorter values
+            #   the model will respond more quickly, but may jump in on short pauses from the
+            #   user.
+            # @param threshold
+            #   Sensitivity threshold (0.0 to 1.0) for voice activity detection. A higher
+            #   threshold will require louder audio to activate the model, and thus might
+            #   perform better in noisy environments.
             def initialize: (
               type: OpenAI::Models::Audio::TranscriptionCreateParams::ChunkingStrategy::VadConfig::type_,
               ?prefix_padding_ms: Integer,

data/sig/openai/models/audio/transcription_diarized.rbs CHANGED Viewed

@@ -11,20 +11,36 @@ module OpenAI
         }
       class TranscriptionDiarized < OpenAI::Internal::Type::BaseModel
+        # Duration of the input audio in seconds.
         attr_accessor duration: Float
+        # Segments of the transcript annotated with timestamps and speaker labels.
         attr_accessor segments: ::Array[OpenAI::Audio::TranscriptionDiarizedSegment]
+        # The type of task that was run. Always `transcribe`.
         attr_accessor task: :transcribe
+        # The concatenated transcript text for the entire audio input.
         attr_accessor text: String
+        # Token or duration usage statistics for the request.
         attr_reader usage: OpenAI::Models::Audio::TranscriptionDiarized::usage?
+        # Token or duration usage statistics for the request.
         def usage=: (
           OpenAI::Models::Audio::TranscriptionDiarized::usage
         ) -> OpenAI::Models::Audio::TranscriptionDiarized::usage
+        # @param duration
+        #   Duration of the input audio in seconds.
+        # @param segments
+        #   Segments of the transcript annotated with timestamps and speaker labels.
+        # @param text
+        #   The concatenated transcript text for the entire audio input.
+        # @param usage
+        #   Token or duration usage statistics for the request.
+        # @param task
+        #   The type of task that was run. Always `transcribe`.
         def initialize: (
           duration: Float,
           segments: ::Array[OpenAI::Audio::TranscriptionDiarizedSegment],
@@ -58,20 +74,36 @@ module OpenAI
             }
           class Tokens < OpenAI::Internal::Type::BaseModel
+            # Number of input tokens billed for this request.
             attr_accessor input_tokens: Integer
+            # Number of output tokens generated.
             attr_accessor output_tokens: Integer
+            # Total number of tokens used (input + output).
             attr_accessor total_tokens: Integer
+            # The type of the usage object. Always `tokens` for this variant.
             attr_accessor type: :tokens
+            # Details about the input tokens billed for this request.
             attr_reader input_token_details: OpenAI::Audio::TranscriptionDiarized::Usage::Tokens::InputTokenDetails?
+            # Details about the input tokens billed for this request.
             def input_token_details=: (
               OpenAI::Audio::TranscriptionDiarized::Usage::Tokens::InputTokenDetails
             ) -> OpenAI::Audio::TranscriptionDiarized::Usage::Tokens::InputTokenDetails
+            # @param input_tokens
+            #   Number of input tokens billed for this request.
+            # @param output_tokens
+            #   Number of output tokens generated.
+            # @param total_tokens
+            #   Total number of tokens used (input + output).
+            # @param input_token_details
+            #   Details about the input tokens billed for this request.
+            # @param type
+            #   The type of the usage object. Always `tokens` for this variant.
             def initialize: (
               input_tokens: Integer,
               output_tokens: Integer,
@@ -92,14 +124,22 @@ module OpenAI
               { ?audio_tokens: Integer, ?text_tokens: Integer }
             class InputTokenDetails < OpenAI::Internal::Type::BaseModel
+              # Number of audio tokens billed for this request.
               attr_reader audio_tokens: Integer?
+              # Number of audio tokens billed for this request.
               def audio_tokens=: (Integer) -> Integer
+              # Number of text tokens billed for this request.
               attr_reader text_tokens: Integer?
+              # Number of text tokens billed for this request.
               def text_tokens=: (Integer) -> Integer
+              # @param audio_tokens
+              #   Number of audio tokens billed for this request.
+              # @param text_tokens
+              #   Number of text tokens billed for this request.
               def initialize: (
                 ?audio_tokens: Integer,
                 ?text_tokens: Integer
@@ -112,10 +152,16 @@ module OpenAI
           type duration = { seconds: Float, ?type: :duration }
           class Duration < OpenAI::Internal::Type::BaseModel
+            # Duration of the input audio in seconds.
             attr_accessor seconds: Float
+            # The type of the usage object. Always `duration` for this variant.
             attr_accessor type: :duration
+            # @param seconds
+            #   Duration of the input audio in seconds.
+            # @param type
+            #   The type of the usage object. Always `duration` for this variant.
             def initialize: (seconds: Float, ?type: :duration) -> void
             def to_hash: -> { seconds: Float, ?type: :duration }

data/sig/openai/models/audio/transcription_diarized_segment.rbs CHANGED Viewed

@@ -12,18 +12,40 @@ module OpenAI
         }
       class TranscriptionDiarizedSegment < OpenAI::Internal::Type::BaseModel
+        # Unique identifier for the segment.
         attr_accessor id: String
+        # End timestamp of the segment in seconds.
         attr_accessor end_: Float
+        # Speaker label for this segment. When known speakers are provided, the label
+        # matches `known_speaker_names[]`. Otherwise speakers are labeled sequentially
+        # using capital letters (`A`, `B`, ...).
         attr_accessor speaker: String
+        # Start timestamp of the segment in seconds.
         attr_accessor start: Float
+        # Transcript text for this segment.
         attr_accessor text: String
+        # The type of the segment. Always `transcript.text.segment`.
         attr_accessor type: :"transcript.text.segment"
+        # @param id
+        #   Unique identifier for the segment.
+        # @param end_
+        #   End timestamp of the segment in seconds.
+        # @param speaker
+        #   Speaker label for this segment. When known speakers are provided, the label
+        #   matches `known_speaker_names[]`. Otherwise speakers are labeled sequentially
+        #   using capital letters (`A`, `B`, ...).
+        # @param start
+        #   Start timestamp of the segment in seconds.
+        # @param text
+        #   Transcript text for this segment.
+        # @param type
+        #   The type of the segment. Always `transcript.text.segment`.
         def initialize: (
           id: String,
           end_: Float,

data/sig/openai/models/audio/transcription_language.rbs CHANGED Viewed

@@ -4,8 +4,11 @@ module OpenAI
       type transcription_language = { code: String }
       class TranscriptionLanguage < OpenAI::Internal::Type::BaseModel
+        # The code of a language detected in the audio.
         attr_accessor code: String
+        # @param code
+        #   The code of a language detected in the audio.
         def initialize: (code: String) -> void
         def to_hash: -> { code: String }

data/sig/openai/models/audio/transcription_segment.rbs CHANGED Viewed

@@ -16,26 +16,62 @@ module OpenAI
         }
       class TranscriptionSegment < OpenAI::Internal::Type::BaseModel
+        # Unique identifier of the segment.
         attr_accessor id: Integer
+        # Average logprob of the segment. If the value is lower than -1, consider the
+        # logprobs failed.
         attr_accessor avg_logprob: Float
+        # Compression ratio of the segment. If the value is greater than 2.4, consider the
+        # compression failed.
         attr_accessor compression_ratio: Float
+        # End time of the segment in seconds.
         attr_accessor end_: Float
+        # Probability of no speech in the segment. If the value is higher than 1.0 and the
+        # `avg_logprob` is below -1, consider this segment silent.
         attr_accessor no_speech_prob: Float
+        # Seek offset of the segment.
         attr_accessor seek: Integer
+        # Start time of the segment in seconds.
         attr_accessor start: Float
+        # Temperature parameter used for generating the segment.
         attr_accessor temperature: Float
+        # Text content of the segment.
         attr_accessor text: String
+        # Array of token IDs for the text content.
         attr_accessor tokens: ::Array[Integer]
+        # @param id
+        #   Unique identifier of the segment.
+        # @param avg_logprob
+        #   Average logprob of the segment. If the value is lower than -1, consider the
+        #   logprobs failed.
+        # @param compression_ratio
+        #   Compression ratio of the segment. If the value is greater than 2.4, consider the
+        #   compression failed.
+        # @param end_
+        #   End time of the segment in seconds.
+        # @param no_speech_prob
+        #   Probability of no speech in the segment. If the value is higher than 1.0 and the
+        #   `avg_logprob` is below -1, consider this segment silent.
+        # @param seek
+        #   Seek offset of the segment.
+        # @param start
+        #   Start time of the segment in seconds.
+        # @param temperature
+        #   Temperature parameter used for generating the segment.
+        # @param text
+        #   Text content of the segment.
+        # @param tokens
+        #   Array of token IDs for the text content.
         def initialize: (
           id: Integer,
           avg_logprob: Float,

data/sig/openai/models/audio/transcription_text_delta_event.rbs CHANGED Viewed

@@ -10,20 +10,43 @@ module OpenAI
         }
       class TranscriptionTextDeltaEvent < OpenAI::Internal::Type::BaseModel
+        # The text delta that was additionally transcribed.
         attr_accessor delta: String
+        # The type of the event. Always `transcript.text.delta`.
         attr_accessor type: :"transcript.text.delta"
+        # The log probabilities of the delta. Only included if you
+        # [create a transcription](https://developers.openai.com/api/reference/resources/audio/subresources/transcriptions/methods/create)
+        # with the `include[]` parameter set to `logprobs`.
         attr_reader logprobs: ::Array[OpenAI::Audio::TranscriptionTextDeltaEvent::Logprob]?
+        # The log probabilities of the delta. Only included if you
+        # [create a transcription](https://developers.openai.com/api/reference/resources/audio/subresources/transcriptions/methods/create)
+        # with the `include[]` parameter set to `logprobs`.
         def logprobs=: (
           ::Array[OpenAI::Audio::TranscriptionTextDeltaEvent::Logprob]
         ) -> ::Array[OpenAI::Audio::TranscriptionTextDeltaEvent::Logprob]
+        # Identifier of the diarized segment that this delta belongs to. Only present when
+        # using `gpt-4o-transcribe-diarize`.
         attr_reader segment_id: String?
+        # Identifier of the diarized segment that this delta belongs to. Only present when
+        # using `gpt-4o-transcribe-diarize`.
         def segment_id=: (String) -> String
+        # @param delta
+        #   The text delta that was additionally transcribed.
+        # @param logprobs
+        #   The log probabilities of the delta. Only included if you
+        #   [create a transcription](https://developers.openai.com/api/reference/resources/audio/subresources/transcriptions/methods/create)
+        #   with the `include[]` parameter set to `logprobs`.
+        # @param segment_id
+        #   Identifier of the diarized segment that this delta belongs to. Only present when
+        #   using `gpt-4o-transcribe-diarize`.
+        # @param type
+        #   The type of the event. Always `transcript.text.delta`.
         def initialize: (
           delta: String,
           ?logprobs: ::Array[OpenAI::Audio::TranscriptionTextDeltaEvent::Logprob],
@@ -42,18 +65,30 @@ module OpenAI
           { ?token: String, ?bytes: ::Array[Integer], ?logprob: Float }
         class Logprob < OpenAI::Internal::Type::BaseModel
+          # The token that was used to generate the log probability.
           attr_reader token: String?
+          # The token that was used to generate the log probability.
           def token=: (String) -> String
+          # The bytes that were used to generate the log probability.
           attr_reader bytes: ::Array[Integer]?
+          # The bytes that were used to generate the log probability.
           def bytes=: (::Array[Integer]) -> ::Array[Integer]
+          # The log probability of the token.
           attr_reader logprob: Float?
+          # The log probability of the token.
           def logprob=: (Float) -> Float
+          # @param token
+          #   The token that was used to generate the log probability.
+          # @param bytes
+          #   The bytes that were used to generate the log probability.
+          # @param logprob
+          #   The log probability of the token.
           def initialize: (
             ?token: String,
             ?bytes: ::Array[Integer],